I want to check the rationale and details of our previous filtering philosophy as Jun had the feeling that we removed too many cells. We also removed too many genes, e.g. highly tissue specific genes such as myl7 are not part of the final data set any longer, which is something that we need to go back on.

sce <- readRDS(paste0(data_dir, "sce_ZF-allSamples-Integrated_2022-01-12_noCounts.rds"))
rownames(sce) <- scater::uniquifyFeatureNames(rowData(sce)$ID, rowData(sce)$Symbol)
sce$old_labels_coarse <- ifelse(grepl("Macrophage", sce$label), "M0",
    ifelse(grepl("T-cells", sce$label), "Tcell",
    ifelse(grepl("Fibroblast", sce$label),"Fibroblast",
        ifelse(grepl("Cardiomyocyte", sce$label), "CM", 
            ifelse(grepl("Endocardium", sce$label),"Endocard.",
                ifelse(grepl("Epicardium", sce$label), "Epicard.",
                    ifelse(grepl("Ery", sce$label), "Ery",
                    ifelse(grepl("eutroph", sce$label), "Neutrophils",
                        ifelse(grepl("delta", sce$label), "delta",
                        ifelse(grepl("EC_", sce$label), "EC",
                            ifelse(grepl("ndothelial", sce$label), "EC", sce$label)))))))))))
sce$old_labels_coarse <- gsub("-cells", "cell", sce$old_labels_coarse)
sce$old_labels_coarse <- gsub("cells$", "", sce$old_labels_coarse)

p1 <-scABC2::plot_reducedDim_from_sce(sce,
    which_reddim = "UMAP", color_by = "hbba1_ENSDARG00000097238",
    exprs_values = "logcounts",
    size_by = .5, alpha = .3, set_colors = FALSE,
    remove_rug=TRUE,
    add_cell_info = c("Tissue","post.surgery")) +
    facet_grid(.~Tissue) + scale_color_viridis_c(direction=-1) +theme(legend.position = "bottom") + ggtitle("Ery marker")

p2 <-dittoSeq::dittoBoxPlot(sce,
    var = "hbba1_ENSDARG00000097238", 
    group.by = "cluster_k200", split.by = "Tissue",
    boxplot.lineweight = 0.1, jitter.size = .2, jitter.width=0.5)

p1 + p2

plot_reducedDim_from_sce(sce[, as.character(sce$cluster_k200) %in% c("7","9","13")],
    which_reddim = "UMAP", 
    color_by = "cluster_k200",
    add_cell_info = "Tissue") +
    facet_wrap(~Tissue)+ ggtitle("Clusters 7, 9, 13 (high Hbba1)")

plot_reducedDim_from_sce(sce, which_reddim = "UMAP", 
    color_by = list(title="Ery label?", 
        result = ifelse(sce$old_labels_coarse == "Ery", TRUE, FALSE)))

plot_reducedDim_from_sce(sce, which_reddim = "UMAP", 
    color_by = list(
        title="Ery label?", 
        result = ifelse(sce$old_labels_coarse == "Ery", TRUE, FALSE)),
    add_cell_info = c("Tissue")) + facet_wrap(~Tissue)

–> check (a) CM markers, (b) liver markers [hepatocytes, cholangiocytes]

Ery vs CM

goidt <- scABC2::make_long_dt(sce, exprs_values = "logcounts",
    features = c("ttn.2","tnni1b", # CM
        "col1a1a", #epicardial
        "hbba1_ENSDARG00000097238", # ery
        "cela1.6", #exocrine pancreas
        "tfa","fabp10a", #hepatocytes,
        "lgals2b", #cholangiocytes
        "colec11", # HepSC
        "itga2b", # megakaryo
        "slc4a1a" # ery
        ),
    include_metaData = c("cluster_k200", "old_labels_coarse","Tissue","Sample","post.surgery","detected","subsets_mito_percent"))

goidt <- dcast(goidt, cell + Tissue + post.surgery + cluster_k200 + Sample + subsets_mito_percent + detected + old_labels_coarse ~ feature_name,  value.var = "logcounts")
setnames(goidt, "hbba1_ENSDARG00000097238", "hbba1")
ggplot(goidt, aes(x = ttn.2, y = hbba1, color = cluster_k200)) + 
    geom_point(size = 1.5, alpha = .2, shape = 1) +
    facet_grid(Tissue~post.surgery) +
    scale_color_manual(values = ABCutilities:::fx.get_palette_ABC("paired_pal")) +
    guides(color = guide_legend(override.aes = list(size = 3, alpha =1, shape = 16) ) )

plot_reducedDim_from_sce(sce[, as.character(sce$cluster_k200) %in% c("7","9","13")],
    which_reddim = "UMAP", 
    color_by = "ttn.2", exprs_values = "logcounts",
    add_cell_info = "Tissue", set_color = FALSE) +
    facet_wrap(~Tissue)+ ggtitle("CM marker", subtitle="Clusters 7, 9, 13 (high Hbba1)") + scale_color_viridis_c(direction = -1, option = "magma")

Ery vs. Liver cells

ggplot(goidt, aes(x = colec11, y = hbba1, color = cluster_k200)) + 
    geom_point(size = 1.5, alpha = .2, shape = 1) +
    facet_grid(Tissue~post.surgery) +
    scale_color_manual(values = ABCutilities:::fx.get_palette_ABC("paired_pal")) +
    guides(color = guide_legend(override.aes = list(size = 3, alpha =1, shape = 16) ) ) +
    ggtitle("Cholangiocyte marker")

ggplot(goidt, aes(x = fabp10a, y = hbba1, color = cluster_k200)) + 
    geom_point(size = 1.5, alpha = .2, shape = 1) +
    facet_grid(Tissue~post.surgery) +
    scale_color_manual(values = ABCutilities:::fx.get_palette_ABC("paired_pal")) +
    guides(color = guide_legend(override.aes = list(size = 3, alpha =1, shape = 16) ) ) +
    ggtitle("Hepatocyte marker")

dittoSeq::dittoBoxPlot(sce[,sce$Tissue=="Liver"], var = "detected",
    group.by = "Sample", split.by = "cluster_k200", 
    boxplot.lineweight = .1, jitter.size = .5, main = "Liver samples only")

plot_reducedDim_from_sce(sce[, sce$Tissue == "Liver"],
    which_reddim = "UMAP", 
    color_by = "subsets_mito_percent", exprs_values = "logcounts",
    add_cell_info = c("cluster_k200","Tissue"), set_color = FALSE) +
    facet_wrap(~Tissue)+ ggtitle("Liver cells only") + 
    scale_color_viridis_c() + facet_wrap(~cluster_k200) +
    theme(legend.position = "bottom")

There seem to be two mito-populations in cluster 7.

ggplot(goidt[Tissue == "Liver"],
    aes(x = fabp10a, y = hbba1, color = subsets_mito_percent)) + 
    geom_point(size = 1.5, alpha = .2, shape = 1) +
    facet_grid(post.surgery~cluster_k200) +
    scale_color_viridis_c()+
    guides(color = guide_legend(override.aes = list(size = 3, alpha =1, shape = 16) ) ) +
    ggtitle("Hepatocytes only") + theme(legend.position = "bottom")

ggplot(goidt[Tissue == "Liver"],
    aes(x = fabp10a, color = hbba1, y = detected)) + 
    geom_point(size = 1.5, alpha = .2, shape = 1) +
    facet_grid(post.surgery~cluster_k200) +
    scale_color_viridis_c(direction=-1, option = "magma")+
    guides(color = guide_legend(override.aes = list(size = 3, alpha =1, shape = 16) ) ) +
    ggtitle("Hepatocytes only") + theme(legend.position = "bottom")

Erys vs acinar/exocrine markers

ggplot(goidt, aes(x = cela1.6, y = hbba1, color = cluster_k200)) + 
    geom_point(size = 1.5, alpha = .2, shape = 1) +
    facet_grid(Tissue~post.surgery) +
    scale_color_manual(values = ABCutilities:::fx.get_palette_ABC("paired_pal")) +
    guides(color = guide_legend(override.aes = list(size = 3, alpha =1, shape = 16) ) ) +
    ggtitle("Acinar cell marker")

Summary